Imbalanced Seismic Event Discrimination Using Supervised Machine Learning
The discrimination between earthquakes and artificial explosions is a significant issue in seismic analysis to efficiently prevent and respond to seismic events. However, the discrimination of seismic events is challenging due to the low incidence rate. Moreover, the similarity between earthquakes a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/6/2219 |
| _version_ | 1797442366759501824 |
|---|---|
| author | Hyeongki Ahn Sangkyeum Kim Kyunghyun Lee Ahyeong Choi Kwanho You |
| author_facet | Hyeongki Ahn Sangkyeum Kim Kyunghyun Lee Ahyeong Choi Kwanho You |
| author_sort | Hyeongki Ahn |
| collection | DOAJ |
| description | The discrimination between earthquakes and artificial explosions is a significant issue in seismic analysis to efficiently prevent and respond to seismic events. However, the discrimination of seismic events is challenging due to the low incidence rate. Moreover, the similarity between earthquakes and artificial explosions with a local magnitude derives a nonlinear data distribution. To improve the discrimination accuracy, this paper proposes machine-learning-based seismic discrimination methods—support vector machine, naive Bayes, and logistic regression. Furthermore, to overcome the nonlinear separation problem, the kernel functions and regularized logistic regression are applied to design seismic classifiers. To efficiently design the classifier, P- and S-wave amplitude ratios on the time domain and spectral ratios on the frequency domain, which is converted by fast Fourier transform and short-time Fourier transform are selected as feature vectors. Furthermore, an adaptive synthetic sampling algorithm is adopted to enhance the classifier performance against the seismic data imbalance issue caused by the non-equivalent number of occurrences. The comparisons among classifiers are evaluated by the binary classification performance analysis methods. |
| first_indexed | 2024-03-09T12:40:51Z |
| format | Article |
| id | doaj.art-65ed57a841f74bb4b3b05f3ab4a80bb6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:40:51Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-65ed57a841f74bb4b3b05f3ab4a80bb62023-11-30T22:17:52ZengMDPI AGSensors1424-82202022-03-01226221910.3390/s22062219Imbalanced Seismic Event Discrimination Using Supervised Machine LearningHyeongki Ahn0Sangkyeum Kim1Kyunghyun Lee2Ahyeong Choi3Kwanho You4Department of Electrical Computer Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Electrical Computer Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Electrical Computer Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Electrical Computer Engineering, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Electrical Computer Engineering, Sungkyunkwan University, Suwon 16419, KoreaThe discrimination between earthquakes and artificial explosions is a significant issue in seismic analysis to efficiently prevent and respond to seismic events. However, the discrimination of seismic events is challenging due to the low incidence rate. Moreover, the similarity between earthquakes and artificial explosions with a local magnitude derives a nonlinear data distribution. To improve the discrimination accuracy, this paper proposes machine-learning-based seismic discrimination methods—support vector machine, naive Bayes, and logistic regression. Furthermore, to overcome the nonlinear separation problem, the kernel functions and regularized logistic regression are applied to design seismic classifiers. To efficiently design the classifier, P- and S-wave amplitude ratios on the time domain and spectral ratios on the frequency domain, which is converted by fast Fourier transform and short-time Fourier transform are selected as feature vectors. Furthermore, an adaptive synthetic sampling algorithm is adopted to enhance the classifier performance against the seismic data imbalance issue caused by the non-equivalent number of occurrences. The comparisons among classifiers are evaluated by the binary classification performance analysis methods.https://www.mdpi.com/1424-8220/22/6/2219seismic discriminationartificial explosionoversampling methodsupervised machine learning |
| spellingShingle | Hyeongki Ahn Sangkyeum Kim Kyunghyun Lee Ahyeong Choi Kwanho You Imbalanced Seismic Event Discrimination Using Supervised Machine Learning Sensors seismic discrimination artificial explosion oversampling method supervised machine learning |
| title | Imbalanced Seismic Event Discrimination Using Supervised Machine Learning |
| title_full | Imbalanced Seismic Event Discrimination Using Supervised Machine Learning |
| title_fullStr | Imbalanced Seismic Event Discrimination Using Supervised Machine Learning |
| title_full_unstemmed | Imbalanced Seismic Event Discrimination Using Supervised Machine Learning |
| title_short | Imbalanced Seismic Event Discrimination Using Supervised Machine Learning |
| title_sort | imbalanced seismic event discrimination using supervised machine learning |
| topic | seismic discrimination artificial explosion oversampling method supervised machine learning |
| url | https://www.mdpi.com/1424-8220/22/6/2219 |
| work_keys_str_mv | AT hyeongkiahn imbalancedseismiceventdiscriminationusingsupervisedmachinelearning AT sangkyeumkim imbalancedseismiceventdiscriminationusingsupervisedmachinelearning AT kyunghyunlee imbalancedseismiceventdiscriminationusingsupervisedmachinelearning AT ahyeongchoi imbalancedseismiceventdiscriminationusingsupervisedmachinelearning AT kwanhoyou imbalancedseismiceventdiscriminationusingsupervisedmachinelearning |